AI agents call basketeer_nutrition to retrieve information from Basketeer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries nutritional information for a product—a classic Read operation. It takes a SKU as input and returns structured nutrition data (macros and micros). There is no creation, modification, deletion, code execution, or financial impact.
From the tool's definition Tool name 'basketeer_nutrition' and description 'Normalized nutrition (typed macros + micros) for a product by SKU' indicates retrieval of nutritional data by product identifier.
Attacks that exploit this kind of access
Normalized nutrition (typed macros + micros) for a product by SKU. It is categorised as a Read tool in the Basketeer MCP Server, which means it retrieves data without modifying state.
Register the Basketeer MCP server in PolicyLayer and add a rule for basketeer_nutrition: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Basketeer. Nothing to install.
basketeer_nutrition is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the basketeer_nutrition rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for basketeer_nutrition. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
basketeer_nutrition is provided by the Basketeer MCP server (tobyandrews1985/basketeer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →